© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 38611
    Prev
    Next
    INDEX
    Explanations

    any or ความ

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ید
    0.90
    ள்
    0.87
    ع
    0.86
    ра
    0.86
    ور
    0.86
    리
    0.85
     pessoal
    0.84
    ुर
    0.82
    시
    0.79
    on
    0.79
    POSITIVE LOGITS
    ,
    0.84
    ן
    0.74
    ta
    0.71
    ird
    0.68
     introdu
    0.68
    i
    0.66
    n
    0.66
    ight
    0.65
    tive
    0.64
     في
    0.64
    Activations Density 0.003%

    No Known Activations